Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2004 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0344. Min Act: -0.0002

Data Index: 936375 (C4 (Web Text))

Max Activating Token Index: 205

Text #1

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0347. Min Act: -0.0002

Data Index: 129520 (C4 (Web Text))

Max Activating Token Index: 670

Text #2

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0329. Min Act: -0.0002

Data Index: 445140 (C4 (Web Text))

Max Activating Token Index: 960

Text #3

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0269. Min Act: -0.0003

Data Index: 743685 (C4 (Web Text))

Max Activating Token Index: 74

Text #4

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0266. Min Act: -0.0003

Data Index: 865887 (C4 (Web Text))

Max Activating Token Index: 438

Text #5

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0276. Min Act: -0.0002

Data Index: 369390 (C4 (Web Text))

Max Activating Token Index: 581

Text #6

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0270. Min Act: -0.0002

Data Index: 468156 (C4 (Web Text))

Max Activating Token Index: 652

Text #7

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0264. Min Act: -0.0003

Data Index: 758544 (C4 (Web Text))

Max Activating Token Index: 715

Text #8

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0267. Min Act: -0.0003

Data Index: 1253769 (C4 (Web Text))

Max Activating Token Index: 778

Text #9

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0254. Min Act: -0.0003

Data Index: 95921 (C4 (Web Text))

Max Activating Token Index: 998

Text #10

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0259. Min Act: -0.0003

Data Index: 1561533 (Python Code)

Max Activating Token Index: 64

Text #11

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0257. Min Act: -0.0002

Data Index: 445993 (C4 (Web Text))

Max Activating Token Index: 297

Text #12

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0272. Min Act: -0.0002

Data Index: 966897 (C4 (Web Text))

Max Activating Token Index: 621

Text #13

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0265. Min Act: -0.0003

Data Index: 67214 (C4 (Web Text))

Max Activating Token Index: 803

Text #14

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0261. Min Act: -0.0002

Data Index: 412944 (C4 (Web Text))

Max Activating Token Index: 402

Text #15

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0254. Min Act: -0.0003

Data Index: 111235 (C4 (Web Text))

Max Activating Token Index: 804

Text #16

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0258. Min Act: -0.0002

Data Index: 941490 (C4 (Web Text))

Max Activating Token Index: 229

Text #17

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0248. Min Act: -0.0002

Data Index: 773741 (C4 (Web Text))

Max Activating Token Index: 508

Text #18

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0238. Min Act: -0.0002

Data Index: 928023 (C4 (Web Text))

Max Activating Token Index: 109

Text #19

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0252. Min Act: -0.0002

Data Index: 1295355 (C4 (Web Text))

Max Activating Token Index: 454